使用 Pytorch 转换和自定义数据集时出错
Error Utilizing Pytorch Transforms and Custom Dataset
这个问题主要涉及 pytorch Dataset 中 __getitem__ 的 return 值，我在源代码中看到它既是元组又是字典。
我一直在关注 this tutorial for creating a dataset class within my code, which is following this tutorial 迁移学习。它具有以下数据集定义。
class FaceLandmarksDataset(Dataset):
"""Face Landmarks dataset."""
def __init__(self, csv_file, root_dir, transform=None):
"""
Args:
csv_file (string): Path to the csv file with annotations.
root_dir (string): Directory with all the images.
transform (callable, optional): Optional transform to be applied
on a sample.
"""
self.landmarks_frame = pd.read_csv(csv_file)
self.root_dir = root_dir
self.transform = transform
def __len__(self):
return len(self.landmarks_frame)
def __getitem__(self, idx):
img_name = os.path.join(self.root_dir,
self.landmarks_frame.iloc[idx, 0])
image = io.imread(img_name)
landmarks = self.landmarks_frame.iloc[idx, 1:].as_matrix()
landmarks = landmarks.astype('float').reshape(-1, 2)
sample = {'image': image, 'landmarks': landmarks}
if self.transform:
sample = self.transform(sample)
return sample
如您所见，__getitem__ return 是一个包含两个条目的字典。
在迁移学习教程中，进行了以下调用来转换数据集：
data_transforms = {
'train': transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'val': transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
}
data_dir = 'hymenoptera_data'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
data_transforms[x])
for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
shuffle=True, num_workers=4)
for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes
use_gpu = torch.cuda.is_available()
inputs, classes = next(iter(dataloaders['train']))
最后一行代码尝试对自定义数据集中的样本进行 运行 转换，导致我的代码出错。
'dict' object has no attribute 'size'
但是如果教程数据集实现正确，它不应该通过转换正确运行吗？我自己的混合实现如下：
import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
from torch.autograd import Variable
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy
from torch.utils.data import *
from skimage import io, transform
plt.ion()
class NumsDataset(Dataset):
"""Face Landmarks dataset."""
def __init__(self, root_dir, transform=None):
"""
Args:
csv_file (string): Path to the csv file with annotations.
root_dir (string): Directory with all the images.
transform (callable, optional): Optional transform to be applied
on a sample.
"""
self.docs = []
for file in os.listdir(root_dir):
#print(file)
if file.endswith(".txt"):
path = os.path.join(root_dir, file)
with open(path, 'r') as f:
self.docs.append( ( file , list(f.read()) ) ) #tup containing file, image values pairs
self.root_dir = root_dir
self.transform = transform
def __len__(self): #returns number of images
i = 0
for j in self.docs:
i += len(j[1])
return i
def len2(self): #returns number of batches
return len(self.docs)
def __getitem__(self, idx):
idx1 = idx // self.len2()
idx2 = idx % self.len2()
imglabel = self.docs[idx1][0] #label with filename for batch error calculation later
imgdir = os.path.join(self.root_dir, self.docs[idx1][0].strip(".txt"))
img = None
l = idx2
for file in os.listdir(imgdir):
file = os.path.join(imgdir, file)
if(l == 0):
img = io.imread(file)
l -= 1
sample = (img , imglabel)
sample ={'image': img, 'label': imglabel}
if self.transform:
sample = self.transform(sample)
return sample
data_transforms = {
'train': transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'val': transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
}
data_dir = "images"
image_datasets = {x: NumsDataset(os.path.join(data_dir, x),
data_transforms[x])
for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=5)
for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = ["one", "two", "four"]
use_gpu = torch.cuda.is_available()
# Get a batch of training data
inputs, classes = next(iter(dataloaders['train']))
目录结构：
images
/train
/file1
*.jpg
/file2...
*.jpg
file1.txt
file2.txt...
/val
/file1
*.jpg
/file2...
*.jpg
file1.txt
file2.txt...
我 return 的示例格式不正确吗？
数据加载教程使用自定义数据集的特定方式是使用自定义转换。转换必须设计为适合数据集。因此，数据集必须输出与库转换函数兼容的样本，或者必须为特定样本案例定义转换。选择后者，除其他外，导致了完整的功能代码。
当您将 dict 而不是 image 传递给 transforms 时，会出现以下问题。示例中提到的自定义转换可以处理该问题，但默认转换不能，您只能将图像传递给转换。这样就解决了一半的问题。
'dict' object has no attribute 'size'
剩下的问题在于示例中的图像处理代码，所以我不得不在 torchvision 中挖掘到 transforms.py；与示例中提到的 skimage 不同，它使用 PIL 图像，所以我用 PIL 替换了代码并且工作得很好。
site-packages/torchvision/transforms/transforms.py
原码：
def __getitem__(self, idx):
if torch.is_tensor(idx):
img_name = os.path.join(self.root_dir,self.anb_frame.iloc[idx, 0])
image = io.imread(img_name)
labels = self.anb_frame.iloc[idx, 1:]
labels = np.array([labels])
sample = {'image': image, 'labels': labels}
if self.transform:
image = self.transform(image)
return sample
修改：
def __getitem__(self, idx):
if torch.is_tensor(idx):
img_name = os.path.join(self.root_dir,self.anb_frame.iloc[idx, 0])
image = Image.open(img_name)
if self.transform:
image = self.transform(image)
labels = self.anb_frame.iloc[idx, 1:]
labels = np.array([labels])
sample = {'image': image, 'labels': labels}
return sample
这个问题主要涉及 pytorch Dataset 中 __getitem__ 的 return 值，我在源代码中看到它既是元组又是字典。
我一直在关注 this tutorial for creating a dataset class within my code, which is following this tutorial 迁移学习。它具有以下数据集定义。
class FaceLandmarksDataset(Dataset):
"""Face Landmarks dataset."""
def __init__(self, csv_file, root_dir, transform=None):
"""
Args:
csv_file (string): Path to the csv file with annotations.
root_dir (string): Directory with all the images.
transform (callable, optional): Optional transform to be applied
on a sample.
"""
self.landmarks_frame = pd.read_csv(csv_file)
self.root_dir = root_dir
self.transform = transform
def __len__(self):
return len(self.landmarks_frame)
def __getitem__(self, idx):
img_name = os.path.join(self.root_dir,
self.landmarks_frame.iloc[idx, 0])
image = io.imread(img_name)
landmarks = self.landmarks_frame.iloc[idx, 1:].as_matrix()
landmarks = landmarks.astype('float').reshape(-1, 2)
sample = {'image': image, 'landmarks': landmarks}
if self.transform:
sample = self.transform(sample)
return sample
如您所见，__getitem__ return 是一个包含两个条目的字典。
在迁移学习教程中，进行了以下调用来转换数据集：
data_transforms = {
'train': transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'val': transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
}
data_dir = 'hymenoptera_data'
image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
data_transforms[x])
for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=4,
shuffle=True, num_workers=4)
for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = image_datasets['train'].classes
use_gpu = torch.cuda.is_available()
inputs, classes = next(iter(dataloaders['train']))
最后一行代码尝试对自定义数据集中的样本进行 运行 转换，导致我的代码出错。
'dict' object has no attribute 'size'
但是如果教程数据集实现正确，它不应该通过转换正确运行吗？我自己的混合实现如下：
import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
from torch.autograd import Variable
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy
from torch.utils.data import *
from skimage import io, transform
plt.ion()
class NumsDataset(Dataset):
"""Face Landmarks dataset."""
def __init__(self, root_dir, transform=None):
"""
Args:
csv_file (string): Path to the csv file with annotations.
root_dir (string): Directory with all the images.
transform (callable, optional): Optional transform to be applied
on a sample.
"""
self.docs = []
for file in os.listdir(root_dir):
#print(file)
if file.endswith(".txt"):
path = os.path.join(root_dir, file)
with open(path, 'r') as f:
self.docs.append( ( file , list(f.read()) ) ) #tup containing file, image values pairs
self.root_dir = root_dir
self.transform = transform
def __len__(self): #returns number of images
i = 0
for j in self.docs:
i += len(j[1])
return i
def len2(self): #returns number of batches
return len(self.docs)
def __getitem__(self, idx):
idx1 = idx // self.len2()
idx2 = idx % self.len2()
imglabel = self.docs[idx1][0] #label with filename for batch error calculation later
imgdir = os.path.join(self.root_dir, self.docs[idx1][0].strip(".txt"))
img = None
l = idx2
for file in os.listdir(imgdir):
file = os.path.join(imgdir, file)
if(l == 0):
img = io.imread(file)
l -= 1
sample = (img , imglabel)
sample ={'image': img, 'label': imglabel}
if self.transform:
sample = self.transform(sample)
return sample
data_transforms = {
'train': transforms.Compose([
transforms.RandomResizedCrop(224),
transforms.RandomHorizontalFlip(),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
'val': transforms.Compose([
transforms.Resize(256),
transforms.CenterCrop(224),
transforms.ToTensor(),
transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
]),
}
data_dir = "images"
image_datasets = {x: NumsDataset(os.path.join(data_dir, x),
data_transforms[x])
for x in ['train', 'val']}
dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=5)
for x in ['train', 'val']}
dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
class_names = ["one", "two", "four"]
use_gpu = torch.cuda.is_available()
# Get a batch of training data
inputs, classes = next(iter(dataloaders['train']))
目录结构：
images
/train
/file1
*.jpg
/file2...
*.jpg
file1.txt
file2.txt...
/val
/file1
*.jpg
/file2...
*.jpg
file1.txt
file2.txt...
我 return 的示例格式不正确吗？
数据加载教程使用自定义数据集的特定方式是使用自定义转换。转换必须设计为适合数据集。因此，数据集必须输出与库转换函数兼容的样本，或者必须为特定样本案例定义转换。选择后者，除其他外，导致了完整的功能代码。
当您将 dict 而不是 image 传递给 transforms 时，会出现以下问题。示例中提到的自定义转换可以处理该问题，但默认转换不能，您只能将图像传递给转换。这样就解决了一半的问题。
'dict' object has no attribute 'size'
剩下的问题在于示例中的图像处理代码，所以我不得不在 torchvision 中挖掘到 transforms.py；与示例中提到的 skimage 不同，它使用 PIL 图像，所以我用 PIL 替换了代码并且工作得很好。
site-packages/torchvision/transforms/transforms.py
原码：
def __getitem__(self, idx):
if torch.is_tensor(idx):
img_name = os.path.join(self.root_dir,self.anb_frame.iloc[idx, 0])
image = io.imread(img_name)
labels = self.anb_frame.iloc[idx, 1:]
labels = np.array([labels])
sample = {'image': image, 'labels': labels}
if self.transform:
image = self.transform(image)
return sample
修改：
def __getitem__(self, idx):
if torch.is_tensor(idx):
img_name = os.path.join(self.root_dir,self.anb_frame.iloc[idx, 0])
image = Image.open(img_name)
if self.transform:
image = self.transform(image)
labels = self.anb_frame.iloc[idx, 1:]
labels = np.array([labels])
sample = {'image': image, 'labels': labels}
return sample